AQ3D: Adaptive Query Transformer for 3D Instance Segmentation

• URL: http://arxiv.org/abs/2608.30618v1
• Date: Mon, 31 Aug 2026 11:27:42 GMT
• Title: AQ3D: Adaptive Query Transformer for 3D Instance Segmentation
• Abstract summary: Transformer-based decoders for 3D instance segmentation typically commit to a fixed number of queries and positional modeling.<n>We present AQ3D, which is designed to handle scenes of various sizes during training and inference.
• Score: 0.0
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Transformer-based decoders for 3D instance segmentation typically commit to a fixed number of queries and positional modeling calibrated on the training distribution rather than on the scene at hand. Indoor scans vary widely in spatial extent and object count, so a fixed query set over-initializes small scenes and under-initializes large ones, while learned absolute and relative encodings are bound to the training scenes' extents and can saturate. We present AQ3D, which is designed to handle scenes of various sizes during training and inference. Queries are instantiated at a fixed ratio of the scene's superpoints, forming an overcomplete set whose background rejection is entirely left to the decoder. Positional information is encoded using 3D RoPE over quantized metric coordinates, replacing learned bounded lookup tables of prior decoders. Further, we improve the decoder itself by using attribution-based superpoint pooling, a mask refinement branch, and a cosine classifier for background rejection. Experiments show our method sets a new state-of-the-art on validation and hidden test splits across the datasets ScanNetV2, ScanNet200, and ScanNet++V2 among decoder methods trained without additional data augmentation. Code is available at \href{https://github.com/kenomo/aq3d}{github.com/kenomo/aq3d}.

Related papers

• TERDNet: Transformer Encoder-Recurrent Decoder Network for Scene Change Detection [4.039245878626346]
  Scene Change Detection (SCD) aims to identify variations between two images of the same location captured at different times.<n>Existing SCD models often overlook the varying importance of features across layers, employ single-step decoders that confine refinement, and provide limited insight into encoder pretraining strategies.<n>We propose TERDNet, a Transformer-Recurrent Decoder Network designed to overcome these limitations.
  arXiv  Detail & Related papers  (2026-05-20T07:18:24Z)
• SigVLP: Sigmoid Volume-Language Pre-Training for Self-Supervised CT-Volume Adaptive Representation Learning [13.428693608916419]
  We introduce a new vision-language model: Sig volumetric.<n>In Sig volumetric, we implement Rotary Position Embedding as the positional encoding method, generating input-conditioned sine and cosine weights on the fly.<n>Our models are trained with the Muon and evaluated on a diverse set of downstream tasks, including zero-shot abnormality and organ classification, segmentation, and retrieval tasks.
  arXiv  Detail & Related papers  (2026-02-25T09:44:27Z)
• PatchAlign3D: Local Feature Alignment for Dense 3D Shape understanding [67.15800065888887]
  Current foundation models for 3D shapes excel at global tasks (retrieval, classification) but transfer poorly to local part-level reasoning.<n>We introduce an encoder-only 3D model that produces language-aligned patch-level features directly from point clouds.<n>Our 3D encoder achieves zero-shot 3D part segmentation with fast single-pass inference without any test-time multi-view rendering.
  arXiv  Detail & Related papers  (2026-01-05T18:55:45Z)
• SGIFormer: Semantic-guided and Geometric-enhanced Interleaving Transformer for 3D Instance Segmentation [14.214197948110115]
  This paper introduces a novel method, named SGIFormer, for 3D instance segmentation. It is composed of the Semantic-guided Mix Query (SMQ) and the Geometric-enhanced Interleaving Transformer (GIT) decoder. It attains state-of-the-art performance on ScanNet V2, ScanNet200, and the challenging high-fidelity ScanNet++ benchmark.
  arXiv  Detail & Related papers  (2024-07-16T10:17:28Z)
• Pixel-Aligned Recurrent Queries for Multi-View 3D Object Detection [16.677107631803327]
  PARQ is a multi-view 3D object detector with transformer and pixel-aligned recurrent queries. It can leverage additional input views without retraining, and can adapt inference compute by changing the number of recurrent iterations.
  arXiv  Detail & Related papers  (2023-10-02T17:58:51Z)
• Mask-Attention-Free Transformer for 3D Instance Segmentation [68.29828726317723]
  transformer-based methods have dominated 3D instance segmentation, where mask attention is commonly involved. We develop a series of position-aware designs to overcome the low-recall issue and perform cross-attention by imposing positional prior. Experiments show that our approach converges 4x faster than existing work, sets a new state of the art on ScanNetv2 3D instance segmentation benchmark, and also demonstrates superior performance across various datasets.
  arXiv  Detail & Related papers  (2023-09-04T16:09:28Z)
• V-DETR: DETR with Vertex Relative Position Encoding for 3D Object Detection [73.37781484123536]
  We introduce a highly performant 3D object detector for point clouds using the DETR framework. To address the limitation, we introduce a novel 3D Relative Position (3DV-RPE) method. We show exceptional results on the challenging ScanNetV2 benchmark.
  arXiv  Detail & Related papers  (2023-08-08T17:14:14Z)
• CMR3D: Contextualized Multi-Stage Refinement for 3D Object Detection [57.44434974289945]
  We propose Contextualized Multi-Stage Refinement for 3D Object Detection (CMR3D) framework. Our framework takes a 3D scene as input and strives to explicitly integrate useful contextual information of the scene. In addition to 3D object detection, we investigate the effectiveness of our framework for the problem of 3D object counting.
  arXiv  Detail & Related papers  (2022-09-13T05:26:09Z)
• Point-M2AE: Multi-scale Masked Autoencoders for Hierarchical Point Cloud Pre-training [56.81809311892475]
  Masked Autoencoders (MAE) have shown great potentials in self-supervised pre-training for language and 2D image transformers. We propose Point-M2AE, a strong Multi-scale MAE pre-training framework for hierarchical self-supervised learning of 3D point clouds.
  arXiv  Detail & Related papers  (2022-05-28T11:22:53Z)
• Implicit Autoencoder for Point-Cloud Self-Supervised Representation Learning [39.521374237630766]
  The most popular and accessible 3D representation, i.e., point clouds, involves discrete samples of the underlying continuous 3D surface. This discretization process introduces sampling variations on the 3D shape, making it challenging to develop transferable knowledge of the true 3D geometry. In the standard autoencoding paradigm, the encoder is compelled to encode not only the 3D geometry but also information on the specific discrete sampling of the 3D shape into the latent code. This is because the point cloud reconstructed by the decoder is considered unacceptable unless there is a perfect mapping between the original and the reconstructed
  arXiv  Detail & Related papers  (2022-01-03T18:05:52Z)
• Temporal-Channel Transformer for 3D Lidar-Based Video Object Detection in Autonomous Driving [121.44554957537613]
  We propose a new transformer, called Temporal-Channel Transformer, to model the spatial-temporal domain and channel domain relationships for video object detecting from Lidar data. Specifically, the temporal-channel encoder of the transformer is designed to encode the information of different channels and frames. We achieve the state-of-the-art performance in grid voxel-based 3D object detection on the nuScenes benchmark.
  arXiv  Detail & Related papers  (2020-11-27T09:35:39Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.